© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 21
    Prev
    Next
    INDEX
    Explanations

    the word "with" along with some surrounding context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.85
     soprav
    -0.77
     Daria
    -0.75
     Sae
    -0.73
    rawDesc
    -0.71
    ReactDOM
    -0.71
     Cæsar
    -0.69
     onOptions
    -0.69
    𝒌
    -0.69
    atoires
    -0.68
    POSITIVE LOGITS
     with
    2.31
    with
    2.19
     With
    2.11
     WITH
    2.11
    With
    1.95
     avec
    1.81
    WITH
    1.80
     Avec
    1.58
    Avec
    1.52
     với
    1.38
    Activations Density 2.597%

    No Known Activations